ML2Motif—Reliable extraction of discriminative sequence motifs from learning machines

Vidovic, Marina M.-C.; Kloft, Marius; Müller, Klaus‐Robert; Görnitz, Nico

doi:10.1371/journal.pone.0174392

Cited by 7 publications

(6 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Techniques of interpretation are also becoming increasingly popular as a tool for exploration and analysis in the sciences. In combination with deep nonlinear machine learning models, they have been able to extract new in-sights from complex physical, chemical, or biological systems [20,21,49,43,54].…”

Section: Introductionmentioning

confidence: 99%

Methods for interpreting and understanding deep neural networks

Montavon

Samek

Müller

2018

Digital Signal Processing

Self Cite

1,906

1,329

View full text Add to dashboard Cite

This paper provides an entry point to the problem of interpreting a deep neural network model and explaining its predictions. It is based on a tutorial given at ICASSP 2017. It introduces some recently proposed techniques of interpretation, along with theory, tricks and recommendations, to make most efficient use of these techniques on real data. It also discusses a number of practical applications.

show abstract

Section: Introductionmentioning

confidence: 99%

Methods for interpreting and understanding deep neural networks

Montavon

Samek

Müller

2018

Digital Signal Processing

Self Cite

1,906

1,329

View full text Add to dashboard Cite

show abstract

“…For example, Sonnenburg et al ( 2008 ) use a string kernel to predict splice sites in C. elegans and extract relevant biological motifs from the resulting positional oligomer importance matrices. The method has since been extended to longer sequence motifs and more general learning procedures (Vidovic et al 2015 , 2017 ). More recently, Kavvas et al ( 2020 ) used an intrinsically interpretable SVM to identify genetic determinants of antimicrobial resistance (AMR) from whole-genome sequencing data.…”

Section: Methodologies and Applicationsmentioning

confidence: 99%

Interpretable machine learning for genomics

Watson

2021

Hum Genet

View full text Add to dashboard Cite

High-throughput technologies such as next-generation sequencing allow biologists to observe cell function with unprecedented resolution, but the resulting datasets are too large and complicated for humans to understand without the aid of advanced statistical methods. Machine learning (ML) algorithms, which are designed to automatically find patterns in data, are well suited to this task. Yet these models are often so complex as to be opaque, leaving researchers with few clues about underlying mechanisms. Interpretable machine learning (iML) is a burgeoning subdiscipline of computational statistics devoted to making the predictions of ML models more intelligible to end users. This article is a gentle and critical introduction to iML, with an emphasis on genomic applications. I define relevant concepts, motivate leading methodologies, and provide a simple typology of existing approaches. I survey recent examples of iML in genomics, demonstrating how such techniques are increasingly integrated into research workflows. I argue that iML solutions are required to realize the promise of precision medicine. However, several open challenges remain. I examine the limitations of current state-of-the-art tools and propose a number of directions for future research. While the horizon for iML in genomics is wide and bright, continued progress requires close collaboration across disciplines.

show abstract

“…to longer sequence motifs and more general learning procedures (Vidovic et al, 2015;Vidovic et al, 2017). More recently, Kavvas et al (2020) used an intrinsically interpretable SVM to identify genetic determinants of antimicrobial resistance (AMR) from whole genome sequencing data.…”

Section: §33 To Discovermentioning

confidence: 99%

Interpretable Machine Learning for Genomics

Watson

2021

Preprint

View full text Add to dashboard Cite

High-throughput technologies such as next generation sequencing allow biologists to observe cell function with unprecedented resolution, but the resulting datasets are too large and complicated for humans to understand without the aid of advanced statistical methods. Machine learning (ML) algorithms, which are designed to automatically find patterns in data, are well suited to this task. Yet these models are often so complex as to be opaque, leaving researchers with few clues about underlying mechanisms. Interpretable machine learning (iML) is a burgeoning subdiscipline of computational statistics devoted to making the predictions of ML models more intelligible to end users. This article is a gentle and critical introduction to iML, with an emphasis on genomic applications. I define relevant concepts, motivate leading methodologies, and provide a simple typology of existing approaches. I survey recent examples of iML in genomics, demonstrating how such techniques are increasingly integrated into research workflows. I argue that iML solutions are required to realize the promise of precision medicine. However, several open challenges remain. I examine the limitations of current state of the art tools and propose a number of directions for future research. While the horizon for iML in genomics is wide and bright, continued progress requires close collaboration across disciplines.

show abstract

ML2Motif—Reliable extraction of discriminative sequence motifs from learning machines

Cited by 7 publications

References 27 publications

Methods for interpreting and understanding deep neural networks

Methods for interpreting and understanding deep neural networks

Interpretable machine learning for genomics

Interpretable Machine Learning for Genomics

Contact Info

Product

Resources

About